This paper proposes a secure active reconfigurable intelligent surfaces (RIS)-assisted multiple input multiple output integrated sensing, communication, and computation over-theair system. Distributed sensors simultaneously sense targets and transmit private data to an access point (AP) via over-the-air computation, while a passive eavesdropper attempts to intercept. We formulate a joint optimization problem to minimize the AP’s computational mean-squared error (MSE) under constraints on the eavesdropper’s computational MSE, sensing accuracy, and transmit power through the jointly design of transmit beam-forming, aggregation beamforming, and active RIS reflection coefficients. Under perfect wiretap channel state information (CSI), the formulated non-convex problem is decomposed and solved via a penalty-based alternating optimization algorithm, using closed-form aggregation beamformer and successive convex approximation. The framework is extended to imperfect wiretap CSI with norm-bounded uncertainty. By deriving a conservative lower bound on the eavesdropper’s distortion and applying the Generalized S-Procedure, a robust alternating optimization algorithm is developed to solve the reformulated problem. Simulations validate the superiority of the proposed scheme over benchmarks with passive or randomly configured active RIS. Key system parameters, including sensor count, security and sensing accuracy thresholds, are analyzed to provide practical insights.